Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Segmentation of liver in abdominal computed tomography (CT) is an important step for radiation therapy planning of hepatocellular carcinoma. Practically, a fully automatic segmentation of liver remains challenging because of low soft tissue contrast between liver and its surrounding organs, and its highly deformable shape. The purpose of this work is to develop a novel superpixel-based and boundary sensitive convolutional neural network (SBBS-CNN) pipeline for automated liver segmentation. The entire CT images were first partitioned into superpixel regions, where nearby pixels with similar CT number were aggregated. Secondly, we converted the conventional binary segmentation into a multinomial classification by labeling the superpixels into three classes: interior liver, liver boundary, and non-liver background. By doing this, the boundary region of the liver was explicitly identified and highlighted for the subsequent classification. Thirdly, we computed an entropy-based saliency map for each CT volume, and leveraged this map to guide the sampling of image patches over the superpixels. In this way, more patches were extracted from informative regions (e.g. the liver boundary with irregular changes) and fewer patches were extracted from homogeneous regions. Finally, deep CNN pipeline was built and trained to predict the probability map of the liver boundary. We tested the proposed algorithm in a cohort of 100 patients. With 10-fold cross validation, the SBBS-CNN achieved mean Dice similarity coefficients of 97.31 ± 0.36% and average symmetric surface distance of 1.77 ± 0.49 mm. Moreover, it showed superior performance in comparison with state-of-art methods, including U-Net, pixel-based CNN, active contour, level-sets and graph-cut algorithms. SBBS-CNN provides an accurate and effective tool for automated liver segmentation. It is also envisioned that the proposed framework is directly applicable in other medical image segmentation scenarios.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931 · cited 1×
“In order to go beyond the local patch-based CNN analysis, a recent studies ( Ronneberger et al., 2015; Milletari et al., 2016) proposed a U-Net network architecture or its variant model to directly analyze the whole imaging data, which takes full advantage of global patterns within the images.”
MethodYushkevich, P. A., Piven, J., Hazlett, H. C., Smith, R. G., Ho, S., Gee, J. C., & Gerig, G. (2006) · NeuroImage · doi:10.1016/j.neuroimage.2006.01.015 · Cited by 8,868
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2538465 · Cited by 2,735 · cited 1×
“A few studies have been made to develop CNN pipelines for medical image segmentation, including segmentations of liver (Hu et al., 2016), prostate (Guo et al., 2016), isointense stage brain tissues (Zhang et al., 2015), brain tumor (Pereira et al., 2016), and pancreas (Roth et al., 2015).”
BackgroundWhat is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153 · cited 1×
“…of each convolution layer can be defined as: where f(·) is an element-wise non-linear transform, here we choose tangent functions tanh for each layer computation, because tanh can produce better a result than sigmoid that has gradient vanishing problem and computation burden (Jarrett et al., 2009).”
BackgroundDeep convolutional neural networks for multi-modality isointense infant brain image segmentation
Zhang, W., Li, R., Deng, H., Wang, L., Lin, W., Ji, S., & Shen, D. (2015) · NeuroImage · doi:10.1016/j.neuroimage.2014.12.061 · Cited by 817 · cited 1×
“A few studies have been made to develop CNN pipelines for medical image segmentation, including segmentations of liver (Hu et al., 2016), prostate (Guo et al., 2016), isointense stage brain tissues (Zhang et al., 2015), brain tumor (Pereira et al., 2016), and pancreas (Roth et al., 2015).”
BackgroundSegmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks
Ibragimov, B., & Xing, L. (2017) · Medical Physics · doi:10.1002/mp.12045 · Cited by 502
Self-citationLong, E., Lin, H., Liu, Z., Wu, X., Wang, L., Jiang, J., An, Y., Lin, Z., Li, X., Chen, J., et al. (2017) · Nature Biomedical Engineering · doi:10.1038/s41551-016-0024 · Cited by 358 · cited 1×
“Recently, deep learning has emerged as a powerful technique for medical image analysis (Litjens et al., 2017; Shen et al., 2017; Ibragimov and Xing, 2017; Bibault et al., 2016; Esteva et al., 2017; Long et al., 2017).”
MethodBig Data and machine learning in radiation oncology: State of the art and future prospects
Bibault, J.-E., Giraud, P., & Burgun, A. (2016) · Cancer Letters · doi:10.1016/j.canlet.2016.05.033 · Cited by 346 · cited 1×
“Recently, deep learning has emerged as a powerful technique for medical image analysis (Litjens et al., 2017; Shen et al., 2017; Ibragimov and Xing, 2017; Bibault et al., 2016; Esteva et al., 2017; Long et al., 2017).”
MethodAutomatic 3D liver location and segmentation via convolutional neural network and graph cut
Lu, F., Wu, F., Hu, P., Peng, Z., & Kong, D. (2017) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-016-1467-3 · Cited by 284 · cited 4×
“We also compared the results with the state-of-art CNN model (Dong et al., 2017) and some representative model-based methods, including active contour Chan-Vese segmentation (Pascal et al, 2012), Graph-cuts (Wu et al., 2016, Jirik et al., 2013) and level-sets (Yushkevich et al., 2006 ).”
MethodInfluentialGhafoorian, M., Karssemeijer, N., Heskes, T., van Uden, I. W. M., Sanchez, C. I., Litjens, G., de Leeuw, F.-E., van Ginneken, B., Marchiori, E., & Platel, B. (2017) · Scientific Reports · doi:10.1038/s41598-017-05300-5 · Cited by 236 · cited 1×
“Therefore, the pixel-based patch-wise or fully CNN may still be challenging in accurately delineatation of the liver organ boundary due to the restriction in memory demanding and highly imbalanced class training set (Chen et al., 2017; Ghafoorian et al., 2017; Han X, 2017).”
BackgroundAutomatic Liver Segmentation Based on Shape Constraints and Deformable Graph Cut in CT Images
Li, G., Chen, X., Shi, F., Zhu, W., Tian, J., & Xiang, D. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2481326 · Cited by 185 · cited 1×
“Among the model-based methods, atlas-based models (Li et al. 2017), graphical models (Wu et al., 2016; Luo et al., 2013), and deformable models(Chartrand et al., 2016; Li et al., 2015) have been proposed.”
Method
Cited by
Seo, H., Huang, C., Bassenne, M., Xiao, R., & Xing, L. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2948320 · Cited by 431
Self-citationCardenas, C. E., Yang, J., Anderson, B. M., Court, L. E., & Brock, K. B. (2019) · Seminars in Radiation Oncology · doi:10.1016/j.semradonc.2019.02.001 · Cited by 407
Survey on deep learning for radiotherapy
Meyer, P., Noblet, V., Mazzara, C., & Lallement, A. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.05.018 · Cited by 302
Seo, H., Badiei Khuzani, M., Vasudevan, V., Huang, C., Ren, H., Xiao, R., Jia, X., & Xing, L. (2020) · Medical Physics · doi:10.1002/mp.13649 · Cited by 300
Self-citationMaximizing impact of explainable artificial intelligence in radiotherapy: a critical review
Heising, L. M., Wolfs, C. J. A., Ou, C. X. J., Hoebers, F. J. P., van Limbergen, E. J., Verhaegen, F., & Jacobs, M. J. G. (2026) · Physics in Medicine & Biology · doi:10.1088/1361-6560/ae25b2 · Cited by 2
Metadata
- Authors
- Qin, W., Wu, J., Han, F., Yuan, Y., Zhao, W., Ibragimov, B., Gu, J., & Xing, L.
- Venue
- Physics in Medicine & Biology
- Publisher
- IOP Publishing
- Published
- 2018-05-04
- Volume
- 63
- Issue
- 9
- Pages
- 095017
- ISSN
- 0031-9155 (ISSN-L)
- 1361-6560
- OpenAlex
- W2796630897
- Cited by
- 106
- References
- 13
- FWCI
- 7.85
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.